Streaming Communication in Multi-Agent Reasoning
- Published
- Source
- arXiv
- Paper number
- 310
- Field
- LLMs / NLP
- arXiv ID
- 2606.05158
Key points
- The paper introduces StreamMA, a multi-agent reasoning system that reduces latency by streaming each reasoning step to downstream agents as soon as it is generated, thereby pipelining neighboring agents.
- Across eight reasoning benchmarks spanning math, science, and code, two state-of-the-art LLMs, Claude Opus 4.6 and GPT-5.4, and three topologies, Chain, Tree, and Graph, StreamMA outperforms both baselines.
- Beyond these contributions, the authors discover a 'step-level scaling law': increasing the number of steps per agent consistently improves both effectiveness and efficiency, and this is a new scaling dimension that is orthogonal to and composable with agent-count scaling.
Paper links
External research summaries. These are not HDATF publications or measured product results.